simpleMultiGPU cudaStreamDestroy cudaFree cudaMallocHost cudaStreamCreate cudaGetDeviceCount cudaFreeHost cudaMalloc cudaSetDevice cudaStreamSynchronize cudaMemcpyAsync whole ./ ../ ../../../Common Asynchronous Data Transfers CUDA Streams and Events Multithreading Multi-GPU Performance multi-GPU support true simpleMultiGPU.cu 1:CUDA Basic Topics sm35 sm37 sm50 sm52 sm53 sm60 sm61 sm70 sm72 sm75 sm80 sm86 sm87 x86_64 linux windows7 x86_64 macosx arm sbsa ppc64le linux all exe